MACHINE LEARNING TECHNIC AND BIG DATA BACKUP

TECHNICAL FIELD

The invention is directed to “the machine learning technic and big data backup” which allows getting bending results much faster and faultlessly by communicating machines with each other that are used for bending with high precision without operator and regardless of the type or strength value of material, especially at plate, profile, and metal forming machines.

STATE OF THE ART

Because of being the profile or plate forming process is done by operators at today’s workshops, industry, etc., and the spring back value that generates while forming the profile or plate is changed according to the material hardness, there is a serious waste of time and salvage costs.

Also, most of these bendings are similar to each other within definite measurements, the same bending diameters can’t be provided even if the materials have the same hardness value. The waste of salvage and time is changed according to the operator, the material’s hardness value varies and it increases the waste of salvage.

The machine CNC transformation attachment that we design to solve that issue with patent number 2022/003965 solves this negation partly. However, because the bending process time will be longer, this method is suitable only for precision works, it can’t upgrade the bending process which he has done with machine learning. In these circumstances, to get more precision and much faster bending works the structuring has to be programmed with machine learning and has to get the old bending process much faster and perfect by taking decisions toward measurements that come after geometrically bending by making benefits from either a piece of pieces of knowledge at big data backup or from the machine’s own memory. PURPOSE OF THE INVENTION

The existing invention is directed to the machine learning technic and big data backup which supplies all the requirements above, eliminates all disadvantages, and provides additional advantages.

The main purpose of the invention is; to make bending faster by structuring that eliminates operator’s skill and provides everybody able to use easily and faultlessly by machine learning method and to learn by benefits from its previous bendings either made by their own or from other machines done and to provide to upgrade bending times.

Another purpose of the invention is; to able to learn through the other machines’ knowledge by connectimg to the big data backup and also to provide other machines benefit by recording their own knowledge.

Another purpose of the invention is; to upgrade the knowledge it learned from its own bendings within the own not only from big data and to provide machine learning without big data connection.

FIGURES

Figure 1 , there is a schematic view of the invention subject product.

USED REFERENCES

10. Big data backup

20. Machine

30. Internet provider DETAILED DESCRIPTION OF INVENTION

In this detailed description, the expression of the invention subject machine learning technic and big data backup is explained by means not to generate any limiting effects and intended to be only understood well of the subject. Figure 1 , there is a schematic view of the invention subject product.

On the system, there are one or more machines (20) that are connected to the big data backup (10) with an internet provider (30).

The working principle of the system is like this:

First bending material is placed on the machine (20) by choosing from the menus according to the specifications. Necessary adjustments are made and bending diameter is defined. After that step, if the machine (20) is connected to the big data backup (10), it continues bending by listing the values after searching according to the bending diameter and material dimensions which are indicated either at its own bending backups or at the big data backup. Bending is done by the machine until reached the bending diameter geometry and when it reached the bending diameter, the material spring back value is calculated by cnc attachment on the machine. It interprets by matching the results at its own backup or at the big data backup according to the ingenerate spring back values. It shortens the finish steps for improving the reaching time to the potential diameter and next spring back value by taking a bending which is done with the nearest values as a reference and it aims to make truer bendings in a faster time by trying to shorten the time and by trying to upgrade the bending at the backup one level more by increasing the pressure value to reach final bending value at 5 times that he reached at 6 times before.

The big data backup that is used in the system, is a kind of structuring like a cloud or it can be worked like a server, web-based backup.

Also, the system can produce machine learning without being connected to the big data, and because of being it learns just from the bendings that it is done by its own, upgrading the time of the bending process takes longer.

Also, the system can produce learning from other machines’ bendings which are inside of a closed cycle by a big data backup that will be built in a plant with a closed cycle.